Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f448144927bcec3b34317d8f9a9849115f50662c3872b8ef201ba2ba8675b8a8
+oid sha256:f7ac93c930d5a289e0a603bd4ca9821cb2fe7c62a3a3c5c3310c5f44fc0cf24c
 size 1195486552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada29d0f30250378e0eb20f6181f28be3cd528d0183137ffe6788c59a519aabd
+oid sha256:5a91b6dc80a4a365a9bda620bd225fed5e866a11489219eca48b921435ceed6c
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802925738f5cf1bd7a28b8cf8d652af7106e40fbe8f3b5856bb8d45ab19696fa
+oid sha256:00dd7b7defb892dd0775dc51bbf68a8c179a96e9e94ca7f2f38209949c0c2e74
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6437a561009636c105274dc962f8693d70870276329964d09cb2a0ab2c2b79f
+oid sha256:6902df8566c998c38360e138b1bfa129e83a9012a2638e0b255cac476fbd4e74
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.091932773590088,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.6342494714587738,
+  "best_metric": 1.8633633852005005,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.8456659619450317,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 15.288,
       "eval_steps_per_second": 3.822,
       "step": 150
+    },
+    {
+      "epoch": 0.6765327695560254,
+      "grad_norm": 5.661881923675537,
+      "learning_rate": 7.699172305235922e-05,
+      "loss": 3.8396,
+      "step": 160
+    },
+    {
+      "epoch": 0.718816067653277,
+      "grad_norm": 7.51119327545166,
+      "learning_rate": 6.035242985127933e-05,
+      "loss": 3.8834,
+      "step": 170
+    },
+    {
+      "epoch": 0.7610993657505285,
+      "grad_norm": 7.847259998321533,
+      "learning_rate": 4.4998460306603325e-05,
+      "loss": 3.938,
+      "step": 180
+    },
+    {
+      "epoch": 0.8033826638477801,
+      "grad_norm": 6.869880676269531,
+      "learning_rate": 3.136214455575538e-05,
+      "loss": 3.6543,
+      "step": 190
+    },
+    {
+      "epoch": 0.8456659619450317,
+      "grad_norm": 22.58540916442871,
+      "learning_rate": 1.9827447816679272e-05,
+      "loss": 3.3961,
+      "step": 200
+    },
+    {
+      "epoch": 0.8456659619450317,
+      "eval_loss": 1.8633633852005005,
+      "eval_runtime": 6.5539,
+      "eval_samples_per_second": 15.258,
+      "eval_steps_per_second": 3.815,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.763619570601165e+16,
+  "total_flos": 3.684826094134886e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null